{"id":"W3212514152","doi":"","title":"Regime Switching Bandits","year":2021,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Markov chain; Markov decision process; Upper and lower bounds; Stochastic matrix; Markov process; Observable; Computer science; State (computer science); Partially observable Markov decision process; Matrix (chemical analysis); Reinforcement learning; Probably approximately correct learning; Artificial intelligence; Mathematical optimization; Mathematics; Markov model; Algorithm; Machine learning; Unsupervised learning; Generalization error; Statistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001695503,0.0001557213,0.0002866695,0.0003405698,0.0004744891,0.002745844,0.0007594021,0.00009541439,0.00008997495],"category_scores_gemma":[0.005072542,0.0001169704,0.00007242373,0.001507304,0.00004092821,0.007364114,0.000234844,0.0002961048,0.0008845954],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008831041,"about_ca_system_score_gemma":0.0002685876,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000141961,"about_ca_topic_score_gemma":0.000003088756,"domain_scores_codex":[0.9957138,0.000184783,0.001099013,0.0002817224,0.002343838,0.0003768156],"domain_scores_gemma":[0.9964792,0.0003704946,0.0005264204,0.0006795596,0.001792809,0.000151502],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005417527,0.00004579893,0.001253835,0.0003078341,0.00001934173,0.00007105109,0.005087363,0.06673161,0.001378365,0.0009930024,0.02852818,0.8955294],"study_design_scores_gemma":[0.0006979033,0.0000413847,0.0012487,0.0001563762,0.000005606272,0.0004826639,0.005695292,0.77073,0.00226205,0.002917672,0.2154088,0.0003536421],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08216947,0.002763913,0.8727208,0.005741459,0.004809103,0.000874462,0.00003958537,0.0006715997,0.0302096],"genre_scores_gemma":[0.9951227,0.000006911885,0.0007822564,0.000303432,0.0002593247,0.0000281405,0.00002444308,0.00001094889,0.003461785],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9129533,"threshold_uncertainty_score":0.9998933,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1121872631780489,"score_gpt":0.4130105025504202,"score_spread":0.3008232393723713,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}